TNG: DeepSeek R1T Chimera

Text input Text output Free Option
Author's Description

DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks. The model merges pretrained weights from both source models to balance performance across reasoning, efficiency, and instruction-following tasks. It is released under the MIT license and intended for research and commercial use.

Key Specifications
Cost
$$$
Context
163K
Parameters
1T
Released
Apr 27, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Logit Bias Temperature Seed Frequency Penalty Max Tokens Include Reasoning Top P Min P Reasoning Logprobs Top Logprobs
Features

This model supports the following features:

Reasoning
Performance Summary

TNG: DeepSeek R1T Chimera, developed by tngtech, demonstrates exceptional performance across several key metrics. It consistently ranks among the fastest models, achieving an Infinityth percentile in speed across seven benchmarks, indicating unparalleled processing efficiency. The model also offers competitive pricing, placing in the 53rd percentile across six benchmarks. Reliability is a significant strength, with a 100% success rate across all seven benchmarks, signifying minimal technical failures and consistent responsiveness. In terms of specific capabilities, DeepSeek R1T Chimera excels in Ethics and General Knowledge, achieving perfect 100% accuracy in both categories, often being the most accurate model at its price point and speed. Its Coding performance is also very strong, with 95% accuracy, placing it in the 97th percentile. Reasoning and Email Classification show solid results at 84% and 98% accuracy respectively. However, a notable weakness is its Instruction Following capability, which yielded very low accuracy (0.0% and 1.0%) in baseline tests, suggesting this area requires significant improvement. Overall, the model leverages its merged DeepSeek-R1 and DeepSeek-V3 architecture to deliver a powerful, reliable, and cost-effective solution, particularly for knowledge-intensive and ethical reasoning tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.18
Completion $0.72

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Chutes
Chutes | tngtech/deepseek-r1t-chimera 163K $0.18 / 1M tokens $0.72 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by tngtech